Related papers: ReXCam: Resource-Efficient, Cross-Camera Video Ana…
Graphics rendering applications increasingly leverage neural networks in tasks such as denoising, supersampling, and frame extrapolation to improve image quality while maintaining frame rates. The temporal coherence inherent in these tasks…
Nowadays, video cameras are deployed in large scale for spatial monitoring of physical places (e.g., surveillance systems in the context of smart cities). The massive camera deployment, however, presents new challenges for analyzing the…
Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing visual analytics systems for multi-camera streams are mostly limited to…
Today, video cameras are deployed in dense for monitoring physical places e.g., city, industrial, or agricultural sites. In the current systems, each camera node sends its feed to a cloud server individually. However, this approach suffers…
In IoT based distributed network of cameras, real-time multi-camera video analytics is challenged by high bandwidth demands and redundant visual data, creating a fundamental tension where reducing data saves network overhead but can degrade…
Deep learning video analytic systems process live video feeds from multiple cameras with computer vision models deployed on edge or cloud. To optimize utility for these systems, which usually corresponds to query accuracy, efficient…
Driven by advances in computer vision and the falling costs of camera hardware, organizations are deploying video cameras en masse for the spatial monitoring of their physical premises. Scaling video analytics to massive camera deployments,…
Video cameras are pervasively deployed in city scale for public good or community safety (i.e. traffic monitoring or suspected person tracking). However, analyzing large scale video feeds in real time is data intensive and poses severe…
Object re-identification (ReID) is committed to searching for objects of the same identity across cameras, and its real-world deployment is gradually increasing. Current ReID methods assume that the deployed system follows the centralized…
Recent advances in video analytics address real-time data drift by continuously retraining specialized, lightweight DNN models for individual cameras. However, the current practice of retraining a separate model for each camera suffers from…
We are concerned with retrieving a query person from multiple videos captured by a non-overlapping camera network. Existing methods often rely on purely visual matching or consider temporal constraints but ignore the spatial information of…
As the number of installed cameras grows, so do the compute resources required to process and analyze all the images captured by these cameras. Video analytics enables new use cases, such as smart cities or autonomous driving. At the same…
Detection-driven real-time video analytics require continuous detection of objects contained in the video frames using deep learning models like YOLOV3, EfficientDet. However, running these detectors on each and every frame in…
Recent works have shown that combining object detection and tracking tasks, in the case of video data, results in higher performance for both tasks, but they require a high frame-rate as a strict requirement for performance. This is…
Traffic cameras are essential in urban areas, playing a crucial role in intelligent transportation systems. Multiple cameras at intersections enhance law enforcement capabilities, traffic management, and pedestrian safety. However,…
We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…
A number of computer vision tasks exploit a succinct representation of the visual content in the form of sets of local features. Given an input image, feature extraction algorithms identify a set of keypoints and assign to each of them a…
Capturing and processing video is increasingly common as cameras become cheaper to deploy. At the same time, rich video understanding methods have progressed greatly in the last decade. As a result, many organizations now have massive…
We introduce ReXTime, a benchmark designed to rigorously test AI models' ability to perform temporal reasoning within video events. Specifically, ReXTime focuses on reasoning across time, i.e. human-like understanding when the question and…
Event cameras encode visual information with high temporal precision, low data-rate, and high-dynamic range. Thanks to these characteristics, event cameras are particularly suited for scenarios with high motion, challenging lighting…